

Rainbow light swirl spinning on black · Photo: Flyd
Stream-R1 依獎勵模型的評分,為每段訓練影片、每個影格和區域加權,在相同速度下於基準測試小幅勝過直接對照的基準方法。
arXiv 預印本 · 2026年5月5日

A dark glass sphere floating over a blurred rainbow of light · Photo: Flyd
一篇預印本發現,量化時的捨入誤差難以預測離散影像 token 保留了什麼,並提出一種平行碼本量化器,在測試過的最大位元預算內持續進步。
arXiv 預印本 · 2026年10月27日

Photo: Hal Gatewood
CodeCap-Bench 評估多模態 AI 模型寫出的程式,能多忠實地重新渲染 323 支 2D 短片,結果發現動態一貫比靜態細節更難掌握。
arXiv 預印本 · 2026年10月27日

Photo: Brecht Corbeel
LatAlignCXR 以解剖結構與病灶位置引導影像生成器;在盲測中,放射科醫師評定它產生的影像空間一致性高於另一套系統。
Scientific Reports · 2026年10月30日System One models such as Jev return decisions through fast, parallel prediction. In this paper, we introduce Jeveration, showing that the same decision paradigm can also generate high-quality images in a single forward pass. Jeveration builds on a frozen vision-language model, repurposing its visual-semantic knowledge for holistic image…
We present Xing 4, a series of large language models that extends the TeleChat lineage through coordinated advances in model architecture and training infrastructure on Ascend. This report describes the design principles and systems engineering behind the series, spanning architecture selection, large-scale pretraining, and reasoning and…
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with both conventional 2D graphical interfaces and complex 3D…
The release of GPT-6 Astra marks the emergence of a new paradigm in robotics: agentic robotics. Within weeks, frontier models with agentic harnesses matched or exceeded task-specific policies on many embodied benchmarks. Instead of training a dedicated policy for each family of tasks, an agentic robotic system applies a foundation model…